Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

BigCodeBench leaderboard — the family board.

3 TRACKED VARIANTS · 2 FIRST-CLASS BOARDS

One family, 3 tracked prints: BigCodeBench (Hard) is cited standalone and keeps live board of its own. Scoring configs and splits of the base board render as sections of this page, each under its own honest label.

● LIVE DATA10 MODELS ON THIS BOARDLEADER MIMO V2 FLASH BASE AT 70.1

First-class boards in this familyCITED STANDALONE · EACH KEEPS ITS OWN LIVE BOARD

#BoardModels scored
01BigCodeBenchTHIS PAGE10

The board — BigCodeBenchTOP 10 OF 10 MEASURED · BEST SCORE PER MODEL, DEFAULT VARIANT

#ModelVendorScoreVLast seen
01MiMo V2 Flash BaseXiaomi70.12026-06-13
02DeepSeek-V3.2-BaseDeepSeek63.92026-06-27
03DeepSeek-V3.1-BaseDeepSeek632026-06-13
04DeepSeek-V3.2-Exp-BaseDeepSeek62.92026-06-13
05Kimi K2 BaseMoonshot61.72026-06-13
06DeepSeek-V4-Pro-BaseDeepSeek59.22026-09-10
07DeepSeek-V4-Flash-BaseDeepSeek56.82026-09-10
08Granite 4.1 30BIBM38.82026-06-15
09Granite 4.1 8BIBM352026-06-15
10Granite 4.1 3BIBM32.22026-06-15
◆ IV — INDEPENDENTLY VERIFIED · ◆ AA — AGGREGATOR · ◆ VA — VENDOR · ◇ SA — SOURCE-ATTRIBUTED

Variants of this boardSCORING CONFIGS & SPLITS — NOT CITED STANDALONE, SO THEY LIVE HERE

BigCodeBench (Full)

VARIANT7 models · best score per model
#ModelVendorScoreVLast seen
01Qwen3 8BAlibaba51.72026-06-05
02Qwen 2.5 Coder 32B InstructAlibaba49.62026-08-23
03Yi Coder 9B Chat01.AI492026-06-05
04Qwen2.5 Coder Instruct 7BAlibaba48.82026-06-05
05DeepSeek-Coder-6.7B-InstructDeepSeek43.82026-06-05
06Llama 3.1 8B InstructMeta40.52026-06-05
07Seed Coder 8B InstructByteDance37.12026-06-05
THE FAMILY BOARD · EVERY PRINT LABELED · EVERY SCORE SOURCE-ATTRIBUTED ON ITS OWN LIVE BOARDAll leaderboardsThe frontier boardModels by vendor